A PyTorch-based Speech Toolkit

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Foundation Architecture for (M)LLMs

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

WaveNet vocoder

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

AI powered speech denoising and enhancement

Controllable and fast Text-to-Speech for over 7000 languages!

SincNet is a neural architecture for efficiently processing raw audio samples.

General Speech Restoration

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

Speech, Language, Audio, Music Processing with Large Language Model

A neural network for end-to-end speech denoising

Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

🔉 spafe: Simplified Python Audio Features Extraction

UniSpeech - Large Scale Self-Supervised Learning for Speech

A python wrapper for Speech Signal Processing Toolkit (SPTK).

Problem Agnostic Speech Encoder